Inspection cleaning method and system, cleaning robot, storage medium and program product

Abstract

The invention relates to an inspection cleaning method and system, a cleaning robot, a storage medium and a program product. The method comprises the steps of generating a target screening area and updating a planning map; determining a target cleaning state based on the target screening area, and determining a target inspection state based on the updated planning map; determining a target task state and a target task path based on the target inspection state and the target cleaning state; and executing an inspection cleaning task based on the target task state and the target task path. By adopting the method, the fluency of the inspection cleaning task can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a patrol cleaning method, system, cleaning robot, storage medium and program product. Background Art

[0002] With the development of artificial intelligence technology, cleaning robots are widely used in various environments. For target areas with uneven garbage distribution, cleaning robots can inspect and clean the target areas by performing patrol cleaning tasks. Compared with performing full-coverage cleaning tasks, performing patrol cleaning tasks can significantly improve the cleaning efficiency of cleaning robots.

[0003] In traditional technology, since the patrol cleaning task involves switching between cleaning mode and patrol mode, complex logic is required to calculate multiple temporary variables, and then determine the working mode and working path of the cleaning robot based on multiple temporary variables. The above process involves a large number of complex calculations and takes a long time, which affects the smoothness of the cleaning robot in performing patrol cleaning tasks. Summary of the Invention

[0004] Based on this, it is necessary to provide a patrol cleaning method, system, cleaning robot, storage medium and program product that can improve the fluency of patrol cleaning tasks in response to the above technical problems.

[0005] In a first aspect, the present application provides a patrol cleaning method. The method comprises:

[0006] Generate target screening areas and update planning maps;

[0007] determining a target cleaning status based on the target screening area, and determining a target inspection status based on the updated planning map;

[0008] Determining a target task state and a target task path based on the target inspection state and the target cleaning state;

[0009] The inspection and cleaning task is executed based on the target task state and the target task path.

[0010] In a second aspect, the present application also provides a patrol cleaning system. The system comprises:

[0011] Inspection module, used to generate target screening areas and update planning maps;

[0012] a determination module, configured to determine a target cleaning state based on the target screening area, and a target inspection state based on the updated planning map;

[0013] A decision module, configured to determine a target task state and a target task path based on the target inspection state and the target cleaning state;

[0014] An execution module is used to execute the inspection and cleaning task based on the target task state and the target task path.

[0015] In a third aspect, the present application further provides a cleaning robot comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0016] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the methods described in the first aspect when the computer program is executed by a processor.

[0017] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps of any one of the methods described in the first aspect when executed by a processor.

[0018] The above-mentioned inspection and cleaning method, system, cleaning robot, storage medium and program product generate a target screening area and an updated planning map; determine the target cleaning state based on the target screening area, and determine the target inspection state based on the updated planning map; determine the target cleaning state based on the target screening area; determine the target task state and target task path based on the target inspection state and target cleaning state; and execute the inspection and cleaning task based on the target task state and target task path. By determining the target inspection state by updating the planning map, determining the target cleaning state by the target screening area, and using the target inspection state and target task state to determine the target task state and target task path for executing the inspection and cleaning task, compared to determining the target task state and target task path through multiple temporary variables, only determining the target inspection state and target cleaning state reduces the amount of calculation for determining the target task state and target task path, shortens the calculation time, and improves the fluency of the cleaning robot in executing the inspection and cleaning task. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A diagram showing an application environment of a patrol cleaning method in one embodiment;

[0021] Figure 2 Schematic diagram of a process of a patrol cleaning method according to an embodiment;

[0022] Figure 3 A schematic diagram of a framework structure for determining a target inspection status by an inspection thread in one embodiment;

[0023] Figure 4 A schematic diagram of a framework structure for determining a global map by a map management thread in one embodiment;

[0024] Figure 5 A schematic diagram of a framework structure for determining a target cleaning state of a cleaning thread in one embodiment;

[0025] Figure 6 is a schematic diagram of a state mapping table in one embodiment;

[0026] Figure 7 A schematic diagram of a framework structure for determining a target task state and a target task path by a main thread in one embodiment;

[0027] Figure 8 A schematic structural diagram of a patrol cleaning system in one embodiment;

[0028] Figure 9 2 is a diagram showing the internal structure of a cleaning robot in one embodiment. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0030] The inspection and cleaning method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. The terminal 102 communicates with the cleaning robot 104 through the network. The terminal 102 and the cleaning robot 104 can be used together to perform the inspection and cleaning method provided in the embodiment of the present application, and the cleaning robot 104 can also be used alone to perform the inspection and cleaning method provided in the embodiment of the present application. The cleaning robot 104 can be various self-moving devices that can perform inspection and cleaning tasks, such as inspection cleaning robots, delivery cleaning robots, guide cleaning robots, automatic guided vehicles (AGVs) and sweepers. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart TVs and smart car-mounted devices, etc., and the portable wearable devices can be smart watches, etc.

[0031] In one embodiment, Figure 2 As shown, a patrol cleaning method is provided, which can be applied to a cleaning robot. This embodiment is described by taking the application of the method to a cleaning robot as an example, and includes steps 202 to 208.

[0032] Step 202: Generate a target screening area and update the planning map.

[0033] Among them, the target screening area refers to the area used to determine the target sequence to be cleaned, which can be understood as the area for screening the objects to be cleaned that are about to be cleaned. The target screening area can be represented by an area of ​​specified color in the screening map. The screening map includes an area of ​​a first color and an area of ​​a second color. The first color and the second color are different. The area of ​​the first color can be used to represent the target screening area, and the area of ​​the second color can be used to represent the non-target screening area. Alternatively, the area of ​​the first color can be used to represent the non-target screening area, and the area of ​​the second color can be used to represent the target screening area. For example, the screening map includes black areas and white areas, the black areas are non-target screening areas, and the white areas are target screening areas. The target screening area corresponds to the current position, that is, if the current position of the cleaning robot changes, the target screening area may also change. The updated planning map refers to a map used to determine the updated inspection path.

[0034] For example, during the execution of a patrol cleaning task, the patrol thread in the cleaning robot obtains the current mode and current position of the cleaning robot, and based on the current mode and current position, generates a target screening area corresponding to the current position; the patrol thread obtains the covered area and the global map, updates the global map based on the covered area, and obtains an updated planning map; the patrol thread determines the target patrol status based on the updated planning map. A patrol cleaning task refers to a task of cleaning the object to be cleaned during the patrol process. During the patrol cleaning task, the cleaning robot switches between patrol mode and cleaning mode, including switching from patrol mode to cleaning mode, and from cleaning mode to patrol mode. The patrol thread refers to a thread that generates a target screening area, generates an updated planning map, determines the target patrol status, and generates an updated patrol path. The patrol thread may correspond to a patrol module, that is, the patrol thread executes tasks in the patrol module. The tasks of the patrol module may be a thread that generates a target screening area, generates an updated planning map, determines the target patrol status, and generates an updated patrol path. The inspection module is a sub-module in the inspection planning framework. The task of the inspection planning framework is to determine the target task status and target task path. The inspection planning framework includes a map management module, an inspection module and a cleaning module. The map management thread performs the tasks of the map management module, the inspection thread performs the tasks of the inspection module, and the cleaning thread performs the tasks of the cleaning module. The current mode refers to the current working mode of the cleaning robot. The current mode can be one of the inspection mode and the cleaning mode. The current position refers to the current position of the cleaning robot. The current position can be expressed in two-dimensional coordinates. The covered area refers to the entire area that has been detected by the cleaning robot's sensors. The global map refers to the environmental map that represents the target area. The target area refers to the area where the cleaning robot performs inspection and cleaning tasks.

[0035] In one embodiment, a schematic diagram of a framework structure of a patrol thread determining a target patrol state, wherein the patrol thread corresponds to the patrol module, that is, the patrol thread executes tasks in the patrol module, such as Figure 3As shown, it includes: in the process of executing the patrol cleaning task, the main thread of the cleaning robot wakes up the patrol thread, the patrol thread obtains the current position and current mode of the cleaning robot from the main thread, determines the target screening area based on the current position and current mode, and outputs the target screening area; the patrol thread records the covered area of ​​the sensor, and outputs the covered area; the patrol thread obtains the global map from the map management thread, updates the global map based on the covered area, and obtains an updated planning map; the patrol thread executes patrol path planning based on the updated planning map, and outputs an updated patrol path; the patrol thread makes a state decision based on the updated patrol path, and outputs the target patrol state. The main thread can include the patrol thread, the map management thread, the cleaning thread, and the thread that determines the target task state and the target task path. It can be understood that the patrol thread, the map management thread, and the cleaning thread are three parallel sub-threads, which respectively execute the tasks of the corresponding modules. The main thread is responsible for scheduling the three parallel sub-threads and making decisions based on the data generated by the three sub-threads.

[0036] In one embodiment, the map management thread determines a schematic diagram of the framework structure of the global map, such as Figure 4 As shown, it includes: the map management thread obtains the initial map corresponding to the inspection and cleaning task according to the task type; the map management thread obtains the perception data through the sensor, and saves the initialized perception data to the perception sequence; the main thread triggers the map management thread to update the initial map, the map management thread obtains the perception sequence, determines the local update area in the initial map based on the perception sequence, and updates the local update area to obtain the global map, and outputs the global map. Among them, perception data refers to the data collected by the sensor, and initialization processing refers to filtering, denoising and other processing of the perception data. The perception sequence refers to the sequence for saving perception data. The local update area refers to the area that needs to be updated in the initial map. The map management thread refers to the thread that generates the perception sequence and outputs the global map. The map management thread can correspond to the map management module, that is, the map management thread executes the tasks in the map management module. The tasks of the map management module can be the thread that generates the perception sequence and outputs the global map.

[0037] In one embodiment, based on the current mode and the current position, a target screening area corresponding to the current position is generated, including: based on the current mode and the current position, determining the target starting path point and the target end path point corresponding to the current position; based on the target starting path point and the target end path point, determining the target screening area corresponding to the current position.

[0038] In one embodiment, based on the current mode and the current position, the target starting path point and the target end path point corresponding to the current position are determined, including: when the current mode is the inspection mode, the inspection path point in the inspection path corresponding to the inspection cleaning task that is closest to the current position is determined as the target matching path point; based on the target matching path point identifier and forward extension length of the target matching path point in the inspection path, the target end path point is determined; based on the target matching path point identifier and backward extension length, the target starting path point is determined.

[0039] In one embodiment, when the current mode is the cleaning mode, the historical end path point and the historical starting path point corresponding to the previous adjacent target screening area are obtained; the current running direction corresponding to the current position and the angle between the reference running direction from the current position to the historical end path point are determined; the straight-line distance between the current position and the historical end path point is determined; based on the angle and the straight-line distance, the target end path point corresponding to the current position is determined; and the historical starting path point is determined as the target starting path point corresponding to the current position.

[0040] Step 204 : determining a target cleaning status based on the target screening area, and determining a target inspection status based on the updated planning map.

[0041] The target cleaning state refers to the current cleaning state, and the cleaning state refers to the cleaning stage. The target cleaning state can be one of: non-cleaning, ready-to-clean, starting cleaning, in-progress, finished cleaning, and returning to inspection. The non-cleaning state refers to a state where cleaning is not required. It can be represented by NORMAL, meaning no objects have been found. The ready-to-clean state refers to a state where cleaning is possible. It can be represented by PREPARE, meaning that a target object has been found, but the cleaning robot may or may not switch to cleaning mode. The cleaning robot may reduce its speed in the ready-to-clean state. The start-cleaning state refers to the state in which preparations are being made for cleaning. It can be represented by START_CLEAN, meaning the robot activates the cleaning device in the ready-to-clean state. The in-progress cleaning state refers to the state in which cleaning is being performed using the cleaning device. It can be represented by CLEANING, meaning the cleaning is complete. The end-cleaning state refers to the state in which cleaning is complete. It can be represented by END_CLEAN, meaning the robot deactivates the cleaning mode in the end-of-clean state. The return patrol state refers to the state of returning to the patrol route. The return patrol state can be represented by RETURN_CRUISE. The target patrol state refers to the current patrol state. The patrol state refers to the patrol stage. The target patrol state can be determined and output by the patrol thread. The target patrol state can be one of the patrol-in-progress state and the patrol-end state. The patrol-in-progress state refers to the state of patrol-in-progress. The patrol-in-progress state can be represented by NORMAL. The patrol-end state refers to the state of patrol-end. The patrol-end state can be represented by FINISHI.

[0042] Exemplarily, in the process of performing the inspection and cleaning task, the inspection thread in the cleaning robot determines the target inspection status based on the updated planning map, the cleaning thread in the cleaning robot obtains the target screening area from the inspection thread, obtains the candidate sequence from the map management thread, screens the candidate data set in the candidate sequence based on the target screening area, obtains the target sequence to be cleaned, and determines the target cleaning status based on the target sequence to be cleaned. Among them, the candidate sequence refers to a sequence composed of candidate data sets, the candidate sequence includes at least one candidate data set, the candidate data set corresponds to the candidate object, and the candidate data set includes but is not limited to candidate object identification, candidate point set, field of view identification and cleaning status identification. The target sequence to be cleaned refers to a sequence composed of data sets to be cleaned, the data set to be cleaned corresponds to the object to be cleaned, and the data set to be cleaned includes but is not limited to object identification and point set to be cleaned.

[0043] In one embodiment, the cleaning thread determines the target cleaning state as shown in the following diagram: Figure 5As shown, it includes: in the process of executing the inspection and cleaning task, the main thread of the cleaning robot wakes up the cleaning thread, the cleaning thread obtains the target screening area from the inspection thread, and obtains the candidate sequence, the cleaned area and the global map from the map management thread; the cleaning thread filters the candidate data set in the candidate sequence based on the target screening area to obtain an updated sequence to be cleaned, determines the target sequence to be cleaned based on the updated area to be cleaned and the cleaned area, and outputs the target sequence to be cleaned; the cleaning thread makes a cleaning state decision based on the target sequence to be cleaned, obtains the target cleaning state, and outputs the target cleaning state; the cleaning thread performs path planning based on the global map and the target sequence to be cleaned, generates an updated cleaning path, and the updated cleaning path can be a cleaning path or a return path, and outputs the updated cleaning path. That is, when the sequence to be cleaned is empty, the generated updated cleaning path is the return path, and when the sequence to be cleaned is not empty, the generated updated cleaning path is the cleaning path. Among them, the cleaning thread refers to the thread that determines the target cleaning state and determines the updated cleaning path. The cleaning thread can correspond to the cleaning module, that is, the cleaning thread executes the tasks in the cleaning module, and the tasks of the cleaning module can be to determine the target cleaning state and determine the updated cleaning path.

[0044] Step 206 : Determine a target task state and a target task path based on the target inspection state and the target cleaning state.

[0045] Among them, the target task state refers to the relevant data used to determine the task parameters of the cleaning robot in the patrol cleaning task, and the target task state includes the target mode and the target state. The target mode refers to the operating mode that the cleaning robot will use, and the target mode is one of the patrol mode and the cleaning mode. The target state refers to the state determined based on the target patrol state and the target cleaning state, and the target state is either the target patrol state or the target cleaning state. The target task path refers to the path that the cleaning robot will use, and the target task path can be the updated patrol path corresponding to the target patrol state, or the updated cleaning path corresponding to the target cleaning state.

[0046] Exemplarily, the main thread of the cleaning robot obtains the target inspection status from the inspection thread, obtains the target cleaning status from the cleaning thread, and determines the target task status and target task path according to the target inspection status and the target cleaning status.

[0047] In one embodiment, the main thread of the cleaning robot obtains the state mapping relationship and determines the target mode and target state corresponding to the target inspection state and the target cleaning state in the mapping relationship as the target task state. The state mapping relationship can be a state mapping table, for example, a schematic diagram of the state mapping table, as shown in FIG. Figure 6As shown, the state mapping table includes candidate inspection states and candidate cleaning states, as well as the correspondence between the target mode and the target state. When the target inspection state and the target cleaning state are known, the candidate inspection state in the state mapping table that is the same as the target inspection state, and the target mode and target state corresponding to the candidate cleaning state that is the same as the target cleaning state, are determined as the target task state. That is, the target mode and target state in the target task state can be determined according to the state mapping table. If the target inspection state is the inspection state and the target cleaning state is the preparation state, then the target mode is the inspection mode, the target state is the preparation state, and the target task state is the inspection mode and the preparation state. Alternatively, if the target inspection state is the inspection state and the target cleaning state is the return inspection state, then the target mode is the cleaning mode, the target state is the return inspection state, and the target task state is the cleaning mode and the return inspection state.

[0048] In one embodiment, the main thread determines the target task state and the target task path. Figure 7 As shown, it includes: in the process of executing the inspection and cleaning task, the main thread obtains the target inspection status and updated inspection path from the inspection thread, and obtains the target cleaning status and updated cleaning path from the cleaning thread; the main thread makes a decision based on the target inspection status, updated inspection path, target cleaning status and updated cleaning path, and obtains the target task status and target task path. More specifically, the main thread determines the target task status based on the target inspection status and the target cleaning status, and determines the target task path from the updated inspection path and the updated cleaning path based on the target task status.

[0049] Step 208: Execute the inspection and cleaning task based on the target task status and the target task path.

[0050] Exemplarily, the cleaning robot performs the patrol cleaning task according to the target task state and the target task path.

[0051] In the above-mentioned inspection and cleaning method, the target inspection status is determined by updating the planning map, and the target cleaning status is determined by the target screening area. The target inspection status and target task status can be used to determine the target task status and target task path for performing the inspection and cleaning task. Compared with determining the target task status and target task path through multiple temporary variables, only determining the target inspection status and target cleaning status reduces the amount of calculation for determining the target task status and target task path, shortens the calculation time, and improves the fluency of the cleaning robot in performing the inspection and cleaning task.

[0052] In one embodiment, determining the target inspection status based on the updated planning map includes:

[0053] An updated inspection path is generated based on the updated planning map; when the updated inspection path is empty, the target inspection state is determined to be the inspection end state; when the updated inspection path is not empty, the target inspection state is determined to be the inspection proceeding state.

[0054] The updated inspection path refers to a path used for inspecting the target area.

[0055] Exemplarily, the cleaning robot generates an updated inspection path based on the updated planning map. If the updated inspection path is empty, the target inspection state is determined to be the end inspection state; if the updated inspection path is not empty, the target inspection state is determined to be the ongoing inspection state.

[0056] In this embodiment, an updated inspection path is generated based on the updated planning map. If the updated inspection path is empty, it means that the updated inspection path has not been generated, that is, the cleaning robot has completed the inspection of the target area, and the target inspection status is determined to be the end inspection status; if the updated inspection path is not empty, it means that the updated inspection path is generated, that is, the cleaning robot has not completed the inspection of the target area, and the target inspection status is determined to be the ongoing inspection status.

[0057] In one embodiment, determining a target cleaning state based on a target screening area includes:

[0058] A candidate sequence is obtained; the candidate sequence includes at least one candidate data set; the candidate data set in the candidate sequence is screened based on a target screening area to obtain a target sequence to be cleaned; and a target cleaning state is determined based on the target sequence to be cleaned.

[0059] Exemplarily, after the cleaning thread in the cleaning robot is awakened by the main thread, the cleaning thread obtains the target screening area from the patrol thread, obtains a candidate sequence including at least one candidate data set from the map management thread, filters the candidate data set in the candidate sequence based on the target screening area, obtains the target sequence to be cleaned, and determines the target cleaning state according to the target sequence to be cleaned.

[0060] In one embodiment, the candidate data set in the candidate sequence is screened based on the target screening area to obtain the target sequence to be cleaned, including: for each candidate data set in the candidate sequence, if the candidate point set in the candidate data set is located in the target screening area, then the current sequence to be cleaned is updated based on the candidate data set to obtain an updated sequence to be cleaned; for each point set to be cleaned in the updated sequence to be cleaned, if at least one point to be cleaned in the point set to be cleaned is located in the cleaned area, then the field of view identifier corresponding to the point set to be cleaned is obtained; when the field of view identifier corresponding to the point set to be cleaned is the first field of view identifier, the points to be cleaned located in the cleaned area are removed from the point set to be cleaned to obtain the target sequence to be cleaned; the first field of view identifier indicates that the object to be cleaned corresponding to the point set to be cleaned is outside the field of view of the cleaning robot.

[0061] In this embodiment, the candidate data set in the candidate sequence is screened through the target screening area to obtain the target sequence to be cleaned. The target sequence to be cleaned refers to a sequence composed of the data sets to be cleaned corresponding to the objects to be cleaned. The target cleaning state is determined based on the target sequence to be cleaned, that is, the current cleaning state is determined according to the screened objects to be cleaned, which provides accurate basic data for the subsequent determination of the target task state and target task path.

[0062] In one embodiment, determining a target cleaning state based on a target sequence to be cleaned includes:

[0063] Obtain the previous adjacent historical cleaning state; if the historical cleaning state is one of the non-cleaning state, the cleaning preparation state, the cleaning state, the cleaning end state and the return inspection state, determine the target cleaning state based on the historical cleaning state and the target to be cleaned sequence.

[0064] The historical cleaning status refers to the most recently determined cleaning status.

[0065] Exemplarily, the cleaning thread in the cleaning robot obtains the previous adjacent historical cleaning status, and when the historical cleaning status is one of the non-cleaning status, the cleaning preparation status, the cleaning status, the cleaning end status and the return inspection status, the target cleaning status is determined based on the historical cleaning status and the target sequence to be cleaned.

[0066] In this embodiment, when the historical cleaning state is one of the non-cleaning state, preparing to clean state, cleaning state, ending cleaning state and returning to inspection state, the target cleaning state is determined through the historical cleaning state and the target to-be-cleaned sequence, providing accurate basic data for the subsequent determination of the target task state and target task path.

[0067] In one embodiment, determining a target cleaning state based on historical cleaning states and a target sequence to be cleaned includes:

[0068] When the historical cleaning state is one of the non-cleaning state and the preparation-to-clean state, the target cleaning state is determined based on the relationship between the interval distance between the object to be cleaned corresponding to the set of points to be cleaned in the target sequence to be cleaned and the cleaning robot and the distance threshold, as well as the historical cleaning state; when the historical cleaning state is one of the cleaning state, the end-of-cleaning state and the return-to-inspection state, the target cleaning state is determined based on the number of sets of points to be cleaned in the target sequence to be cleaned and the historical cleaning state.

[0069] The "point set to be cleaned" refers to a set of points representing the object to be cleaned, and the point set to be cleaned includes multiple points to be cleaned. The "object to be cleaned" refers to the object represented by the "point set to be cleaned." The "interval distance" refers to the straight-line distance between the object to be cleaned and the cleaning robot. The "distance threshold" refers to a value used for comparison with the interval distance. The distance threshold can be determined based on the length of the target screening area, and the distance threshold is less than the length of the target screening area.

[0070] Exemplarily, when the historical cleaning state is one of the non-cleaning state and the ready-to-clean state, the cleaning thread in the cleaning robot determines the center position of each set of points to be cleaned in the target sequence to be cleaned, calculates the straight-line distance between the center position and the current position of the cleaning robot, and obtains the interval distance corresponding to the set of points to be cleaned; compares the interval distance corresponding to each set of points to be cleaned with the distance threshold to obtain a comparison result, and determines the target cleaning state based on the comparison result and the historical cleaning state. When the historical cleaning state is one of the cleaning state, the end cleaning state, and the return to inspection state, the cleaning thread in the cleaning robot determines the number of set of points to be cleaned in the target sequence to be cleaned, and determines the target cleaning state based on the number of set of points to be cleaned in the target sequence to be cleaned and the historical cleaning state. The center position can be the center point of the minimum circumscribed circle of the set of points to be cleaned.

[0071] In one embodiment, when the historical cleaning state is a non-cleaning state, if the interval distances corresponding to all the sets of points to be cleaned in the sequence to be cleaned are greater than the distance threshold, the target cleaning state is determined to be a ready-to-clean state; if the interval distances corresponding to at least one set of points to be cleaned in the sequence to be cleaned are less than the distance threshold, the target cleaning state is determined to be a start-cleaning state.

[0072] In one embodiment, when the historical cleaning state is the ready-to-clean state, if the interval distances corresponding to all the sets of points to be cleaned in the sequence to be cleaned are greater than the distance threshold, the target cleaning state is determined to be the ready-to-clean state; if the interval distance corresponding to at least one set of points to be cleaned in the sequence to be cleaned is less than the distance threshold, the target cleaning state is determined to be the start-to-clean state.

[0073] In one embodiment, when the historical cleaning state is the cleaning state, if the number of point sets to be cleaned in the target to-clean sequence is zero, the target cleaning state is determined to be the end cleaning state; if the number of point sets to be cleaned in the target to-clean sequence is not zero, the target cleaning state is determined to be the cleaning state.

[0074] In one embodiment, when the historical cleaning state is the end cleaning state, if the number of the set of points to be cleaned in the target to-be-cleaned sequence is zero, the target cleaning state is determined to be the return inspection state; if the number of the set of points to be cleaned in the target to-be-cleaned sequence is not zero, the target cleaning state is determined to be the start cleaning state.

[0075] In one embodiment, when the historical cleaning state is the return inspection state, if the number of the to-be-cleaned point sets in the target to-be-cleaned sequence is zero and the cleaning robot has not returned to the inspection path, the target cleaning state is determined to be the return inspection state; if the number of the to-be-cleaned point sets in the target to-be-cleaned sequence is zero and the cleaning robot returns to the inspection path, the target cleaning state is determined to be the non-cleaning state; if the number of the to-be-cleaned point sets in the target to-be-cleaned sequence is not zero, the target cleaning state is determined to be the start cleaning state.

[0076] In one embodiment, when the historical cleaning state is the start cleaning state, the target cleaning state is determined to be the ongoing cleaning state.

[0077] In this embodiment, when the historical cleaning state is one of the non-cleaning state and the preparation for cleaning state, the target cleaning state is determined based on the size relationship between the interval distance corresponding to the set of points to be cleaned in the target sequence to be cleaned and the distance threshold and the historical cleaning state. When the historical cleaning state is one of the cleaning state, the end cleaning state and the return inspection state, the target cleaning state is determined based on the number of sets of points to be cleaned in the target sequence to be cleaned and the historical cleaning state. For incorrect historical cleaning states, different methods are used to determine the target cleaning state, which improves the accuracy of the target cleaning state and provides accurate basic data for the subsequent determination of the target task state and target task path.

[0078] In one embodiment, determining a target task state and a target task path based on a target inspection state and a target cleaning state includes:

[0079] Based on the target inspection state and the target cleaning state, a target mode and a target state in the target task state are determined; the target task state is used to determine the task parameters of the cleaning robot in the inspection and cleaning task;

[0080] Based on the target pattern, determine the target task path.

[0081] Among them, task parameters refer to parameters for executing inspection and cleaning tasks. Task parameters include but are not limited to at least one of operating parameters and cleaning parameters. Operating parameters can be operating speed and obstacle avoidance methods, etc. Cleaning parameters can be roller brush speed, suction strength and water tank flow, etc.

[0082] Exemplarily, the main thread in the cleaning robot obtains the target inspection status from the patrol thread, obtains the target cleaning status from the cleaning thread, obtains the state mapping relationship, determines the target mode and target state corresponding to the target inspection status and target cleaning status in the mapping relationship as the target task state, and determines the task parameters of the cleaning robot in the patrol cleaning task according to the target task state; when the target mode is the patrol mode, the main thread determines the updated patrol path obtained from the patrol thread as the target task path, and when the target mode is the cleaning mode, the main thread determines the updated cleaning path obtained from the cleaning thread as the target task path.

[0083] In this embodiment, the target mode and target state in the target task state are determined through the target inspection state and the target cleaning state. The target task path is determined based on the target mode. The target task state provides the cleaning robot with the task parameters in the patrol cleaning task, and the target task path provides the cleaning robot with the path in the patrol cleaning task, laying the foundation for the cleaning robot to perform the cleaning inspection task.

[0084] In an exemplary embodiment, the cleaning robot uses a patrol task framework to determine the target task status and target task path. The cleaning robot performs patrol cleaning tasks based on the target task status and target task path. The patrol task framework includes a map management module, an inspection module and a cleaning module. The patrol task framework uses multi-threading technology, including a main thread, a map management thread corresponding to the map management module, a patrol thread corresponding to the inspection module and a cleaning thread corresponding to the cleaning module.

[0085] The map management thread obtains the initial map corresponding to the inspection and cleaning task; the map management thread obtains perception data through sensors and saves the initialized perception data to the perception sequence; the main thread triggers the map management thread to update the initial map, the map management thread obtains the perception sequence, determines the local update area in the initial map based on the perception sequence, and updates the local update area to obtain the global map, and outputs the global map.

[0086] During the execution of the patrol cleaning task, the main thread wakes up the patrol thread, the patrol thread obtains the current position and current mode of the cleaning robot from the main thread, determines the target screening area based on the current position and current mode, and outputs the target screening area; the patrol thread records the covered area of ​​the sensor, and outputs the covered area; the patrol thread obtains the global map from the map management thread, updates the global map based on the covered area, and obtains an updated planning map; the patrol thread executes patrol path planning based on the updated planning map, and outputs an updated patrol path; the patrol thread makes status decisions based on the updated patrol path, and outputs the target patrol status.

[0087] During the execution of the inspection and cleaning task, the main thread wakes up the cleaning thread, the cleaning thread obtains the target screening area from the inspection thread, obtains the candidate sequence and the cleaned area from the map management thread, filters the candidate data set in the candidate sequence based on the target screening area, obtains the updated sequence to be cleaned, determines the target sequence to be cleaned based on the updated area to be cleaned and the cleaned area, and outputs the target sequence to be cleaned; the cleaning thread makes a cleaning status decision based on the target sequence to be cleaned, obtains the target cleaning status, and outputs the target cleaning status; the cleaning thread obtains the global map from the map management thread, generates an updated cleaning path based on the global map and the target sequence to be cleaned, the updated cleaning path can be a cleaning path or a return path, and outputs the updated cleaning path.

[0088] During the execution of the inspection and cleaning tasks, the main thread obtains the target inspection status and updated inspection path from the inspection thread, and obtains the target cleaning status and updated cleaning path from the cleaning thread; the main thread determines the target task status based on the target inspection status and target cleaning status; the main thread determines the target task path from the updated inspection path and updated cleaning path based on the target task status.

[0089] In the above-mentioned inspection and cleaning method, the target inspection state is determined by updating the planning map, and the target cleaning state is determined by using the target screening area. The target inspection state and target task state are used to determine the target task state and target task path for executing the inspection and cleaning task. Compared with determining the target task state and target task path through multiple temporary variables, determining only the target inspection state and target cleaning state reduces the amount of calculation required to determine the target task state and target task path, shortens the calculation time, and improves the smoothness of the cleaning robot in executing the inspection and cleaning task. Moreover, by using multi-threading technology, the decision-making time is shortened, further improving the smoothness of the cleaning robot in executing the inspection and cleaning task.

[0090] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0091] Based on the same inventive concept, the present application also provides an inspection and cleaning system for implementing the inspection and cleaning method described above. The solution provided by this system is similar to the solution described in the method described above. Therefore, the specific limitations of one or more inspection and cleaning system embodiments provided below can be found in the above-mentioned limitations of the inspection and cleaning method and will not be repeated here.

[0092] In one embodiment, Figure 8 As shown, a patrol cleaning system is provided, including: a patrol module 802, a determination module 804, a decision module 806 and an execution module 808, wherein:

[0093] Inspection module 802, used to generate target screening areas and update planning maps;

[0094] a determination module 804 for determining a target cleaning state based on the target screening area and a target inspection state based on the updated planning map;

[0095] A decision module 806 is configured to determine a target task state and a target task path based on the target inspection state and the target cleaning state;

[0096] The execution module 808 is used to execute the inspection and cleaning task based on the target task state and the target task path.

[0097] In one embodiment, the inspection module 802 is also used to: generate an updated inspection path based on the updated planning map; when the updated inspection path is empty, determine the target inspection state to be the end inspection state; when the updated inspection path is not empty, determine the target inspection state to be the ongoing inspection state.

[0098] In one embodiment, the determination module 804 is further used to: obtain a candidate sequence; the candidate sequence includes at least one candidate data set; filter the candidate data set in the candidate sequence based on the target screening area to obtain a target sequence to be cleaned; and determine a target cleaning state based on the target sequence to be cleaned.

[0099] In one embodiment, the determination module 804 is also used to: obtain the previous adjacent historical cleaning status; when the historical cleaning status is one of the non-cleaning status, the cleaning preparation status, the cleaning status, the cleaning end status and the return inspection status, determine the target cleaning status based on the historical cleaning status and the target to-be-cleaned sequence.

[0100] In one embodiment, the determination module 804 is also used to: determine the target cleaning state based on the relationship between the interval distance between the object to be cleaned corresponding to the set of points to be cleaned in the target cleaning sequence and the cleaning robot and the distance threshold, as well as the historical cleaning state when the historical cleaning state is one of the non-cleaning state and the preparation for cleaning state; determine the target cleaning state based on the number of the set of points to be cleaned in the target cleaning sequence and the historical cleaning state when the historical cleaning state is one of the cleaning state, the end cleaning state and the return inspection state.

[0101] In one embodiment, the decision module 806 is also used to: determine the target mode and target state in the target task state based on the target inspection state and the target cleaning state; the target task state is used to determine the task parameters of the cleaning robot in the inspection and cleaning task; and determine the target task path based on the target mode.

[0102] Each module in the above-mentioned inspection and cleaning system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the robot's processor in hardware form, or can be stored in the robot's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0103] In one embodiment, a cleaning robot is provided. The cleaning robot may be a terminal, and its internal structure may be as shown in FIG. Figure 9As shown. The cleaning robot includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The cleaning robot's processor provides computing and control capabilities. The cleaning robot's memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage medium. The cleaning robot's input / output interface is used to exchange information between the processor and external devices. The cleaning robot's communication interface is used to communicate with external terminals via wired or wireless means, with wireless communication being achieved via Wi-Fi, mobile cellular networks, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a patrol cleaning method. The cleaning robot's display unit is used to produce visually visible images and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the cleaning robot can be a touch layer covering the display screen, or a button, trackball or touchpad set on the cleaning robot shell, or an external keyboard, touchpad or mouse.

[0104] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the cleaning robot to which the solution of the present application is applied. The specific cleaning robot may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0105] In one embodiment, a cleaning robot is provided, comprising a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0106] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0107] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0108] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0109] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0110] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A patrol cleaning method, characterized in that: The method is used for a cleaning robot, comprising: Generate target screening areas and update planning maps; determining a target cleaning status based on the target screening area, and determining a target inspection status based on the updated planning map; Determining a target task state and a target task path based on the target inspection state and the target cleaning state; The inspection and cleaning task is executed based on the target task state and the target task path.

2. The method according to claim 1, characterized in that The determining of the target inspection status based on the updated planning map includes: generating an updated inspection route based on the updated planning map; When the updated inspection path is empty, determining the target inspection state to be the inspection end state; When the updated inspection path is not empty, the target inspection state is determined to be an inspection-in-progress state.

3. The method according to claim 1, characterized in that Determining a target cleaning state based on the target screening area includes: Acquire a candidate sequence; the candidate sequence includes at least one candidate data set; Screening the candidate data set in the candidate sequence based on the target screening area to obtain a target sequence to be cleaned; Based on the target sequence to be cleaned, a target cleaning state is determined.

4. The method according to claim 3, characterized in that The determining of a target cleaning state based on the target sequence to be cleaned includes: Get the previous adjacent historical cleaning status; When the historical cleaning state is one of a non-cleaning state, a cleaning preparation state, a cleaning process state, a cleaning end state, and a return inspection state, a target cleaning state is determined based on the historical cleaning state and the target sequence to be cleaned.

5. The method according to claim 4, characterized in that The determining of a target cleaning state based on the historical cleaning state and the target sequence to be cleaned includes: In a case where the historical cleaning state is one of a non-cleaning state and a ready-to-clean state, determining a target cleaning state based on a relationship between a distance between an object to be cleaned corresponding to a set of points to be cleaned in the target to-clean sequence and the cleaning robot and a distance threshold, as well as the historical cleaning state; When the historical cleaning state is one of a cleaning state, a cleaning end state, and a return inspection state, a target cleaning state is determined based on the number of to-be-cleaned point sets in the target to-be-cleaned sequence and the historical cleaning state.

6. The method according to claim 1, characterized in that The determining of a target task state and a target task path based on the target inspection state and the target cleaning state includes: Based on the target inspection state and the target cleaning state, determining a target mode and a target state in the target task state; the target task state is used to determine task parameters of the cleaning robot in the inspection and cleaning task; Based on the target pattern, a target task path is determined.

7. A patrol cleaning system, characterized in that: The system is used for a cleaning robot, comprising: Inspection module, used to generate target screening areas and update planning maps; a determination module, configured to determine a target cleaning state based on the target screening area, and a target inspection state based on the updated planning map; A decision module, configured to determine a target task state and a target task path based on the target inspection state and the target cleaning state; An execution module is used to execute the inspection and cleaning task based on the target task state and the target task path.

8. A cleaning robot comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images